Continue to Site

Welcome to EDAboard.com

Welcome to our site! EDAboard.com is an international Electronics Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.

How to calculate the depth of FIFO?

Status
Not open for further replies.

Richard Lee

Newbie level 4
Joined
Jun 17, 2004
Messages
5
Helped
0
Reputation
0
Reaction score
0
Trophy points
1,281
Location
Taiwan
Activity points
46
I got a question from my friend. Where can I get the related information?

---------------------------------------------------------------------------------
[Sender] --> [FIFO] --> [Receiver]

Sender sends data at the rate of 80 words / 100 clocks
Receiver can consume at the rate of 8 words / 10 clocks

Calculate the depth of FIFO so that no data is dropped.
Assumptions: There is no feedback or handshake mechanism. Occurrence of data in that time period is guaranteed but exact place in those clock cycles is indeterminate.
 

hi,
You can find the resolvent in <Queuing Theory>.
Suppose the times of input and output data as throughput.
It will calculate the buf size. It is the depth of FIFO.

Good Luck
 

consider worst case condition.. say in first 80 clocks 80 words are given to the input.. but at output .worst data reading rate is 8word/10clock .. ie in 80 clocks 64 words might have been read.. so the FIFO depth required is 16..
 

whatever whizkid said is true. but we can consider even more worst case.
Lets say in the 200 clock cycles we receive data for 160 clocks continuously. Then we require a FIFO of depth 32 not 16.
So the correct answer will be 32.
 

I think the depth is 16
 

I think 32(or 33) is correct.

The worst case is then two writes (80words for each) are continuous in two 100-clock slots


1------20-----------------100 101------------------181--------200
   WWWWWWWWWW WWWWWWWWWW
   RRRRRRRRRRRRRRR RRRRRRRRRRRRRRR
This scenario will left 32words unread.
 

the question does not mention the width of write port or read port.

In absence of that, I can even assume that its possible to write 80 words in last cycle and still satisfy the conditions in quesiton. So for first 99 cycles sender doesnot do any write, and reciever sees a fifo underrun ??
 

I got a question from my friend. Where can I get the related information?

---------------------------------------------------------------------------------
[Sender] --> [FIFO] --> [Receiver]

Sender sends data at the rate of 80 words / 100 clocks
Receiver can consume at the rate of 8 words / 10 clocks

Calculate the depth of FIFO so that no data is dropped.
Assumptions: There is no feedback or handshake mechanism. Occurrence of data in that time period is guaranteed but exact place in those clock cycles is indeterminate.

this is the synchronous fifo so no need of depth calculation required default u can take 16 or 32 is enough.
 

Status
Not open for further replies.

Part and Inventory Search

Welcome to EDABoard.com

Sponsor

Back
Top